Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7621
    Prev
    Next
    INDEX
    Explanations

    mentions of users or user-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to user-related concepts and interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaugh
    -0.64
     Beir
    -0.64
     Roof
    -0.64
    amer
    -0.63
     Winning
    -0.62
     Tempest
    -0.61
     Baptist
    -0.60
    LECT
    -0.60
    forth
    -0.60
     offic
    -0.59
    POSITIVE LOGITS
     interface
    1.20
    interface
    1.11
     interfaces
    1.08
     Interface
    1.08
    agent
    0.98
    pace
    0.98
    Agent
    0.97
    cript
    0.94
    base
    0.94
    Interface
    0.86
    Activations Density 0.039%

    No Known Activations